Condition-Based Monitoring (CBM) is a key approach in predictive maintenance, enabling real-time assessment of component integrity to optimize maintenance strategies and extend component life. In aircraft engine systems, baffles play a crucial role in directing airflow for cooling, preventing overheating, and ensuring operational efficiency. However, continuous exposure to thermal stress, vibration, and mechanical fatigue leads to baffle degradation, impacting engine performance and safety. This study addresses a critical gap in the literature by applying Natural Language Processing (NLP) techniques to analyse text-based maintenance logs for component-level condition assessment-an area largely overlooked in aviation maintenance research. Using Nestor, an NLP tool developed by the National Institute of Standards and Technology (NIST), text-based maintenance logs from the MainNet open-source library are analysed to detect failure patterns and support Life Extension (LE) decisions. A structured condition assessment model evaluates key indicators such as crack length, drilled holes, rivet applications, thermal cycles, vibration stress, and material aging. Baffles are classified into three categories: Good Condition, Repair Condition, and Replacement Condition, enabling data-driven maintenance decisions and reducing unnecessary replacements. While promising, the approach also faces challenges related to data quality variability, NLP domain adaptation, and broader generalizability across diverse aviation datasets. The findings demonstrate that integrating CBM with text-based analytics enhances failure detection and predictive maintenance strategies. Future research should explore combining NLP-driven analysis with sensor-based monitoring and machine learning techniques to further improve predictive capabilities and maintenance efficiency.