In this paper, we present a system for image replica detection. The technique is based on the extraction of 162 features corresponding to texture, colour and grey-level characteristics. These features are then weighted and statistically normalized. To improve computational complexity of the training, and performance, features space dimensionality is reduced. Finally, a decision function is generated to classify the test image as a replica or a non-replica of the reference image. Experimental results show the effectiveness of the proposed system. Target applications include search for copyright infringement (e.g. variations of copyrighted images) and illicit content (e.g. paedophile images).