In last years, multimedia content has grown increasingly over the Internet, especially in social networks, where users often post images using their mobile devices. Currently searching into these networks is primarily made using the title and the keywords associated to resources added by users that have posted the images. The problem we face comes from the fact that many times, title or related keywords are not relevant to the image content. The project presented in this article, has expanded a gold collection of annotated images that will be further processed in order to find similar images based on image content.