When thinking of aligning MRI or X-ray scans taken before and after treatment, feature matching can help identify corresponding points in these scans to align them accurately and avoid manual procedures. This might involve matching features like the edges of tumors or organs across different scans using a feature detector. These features are matched across scans, and transformations (rigid or non-rigid) are applied to align the images, helping doctors see changes over time or combine different scan types for better diagnosis. Even though feature matching has improved over the years and introduced more complex algorithms and structures like neural networks, with better results but higher processing costs and training needs, it hasn’t completely resolved the alignment on difficult and challenging medical studies, mismatching some selected points and misaligning the final result. For this reason, we propose a statistical comparison between different feature matching algorithms used in semi-automatic and automatic workflows, to search for a simple approximation to the rigid alignment of medical images with low computation resources.