Abstract
In this paper, we propose a medical content based image retrieval system based on efficient discrimination between visual descriptors within each image category. In addition, the proposed approach reduces the search space during the retrieval phase by incorporating an unsupervised learning and feature weighing component. We use a collection of X-ray images from ImageCLEF2009 data set in order to assess the performance of the system. The obtained results show that the proposed approach is faster than typical content based image retrieval.