Lung cancer remains a massive issue within the medical profession, with a considerable number of cases reported worldwide today. The number of undetected cases is increasing every year, with devastating consequences. As we all know, early detection can mean the difference between saving a life and losing a life. Early detection is hard due to the lack of symptoms; for example, the characteristics of a tumor are very difficult to detect. However, Computed Tomography (CT) imaging can play a crucial role in diagnosis, as it is known to cause errors in the detection of lung cancer. To better understand the stage of cancer and what we can do to help a patient, our study proposes a hybrid deep learning model that will automatically classify lung cancer from CT scanning by combining the strengths of two pre-trained convolutional neural networks, VGG16 and ResNet50. The model was trained and evaluated on the publicly available IQ-OTH/NCCD dataset, utilizing data augmentation techniques to find a way to address the class imbalance that we are facing. Experiments showed that the proposed model offered exceptional performance, with an accuracy of 98.18% and high precision and recall for all classes. The hybrid system outperformed previous work and shows strong potential for clinical application. However, as the evaluation was performed on a single dataset, future external validation is necessary.