Multimedia content has become an essential tool to share knowledge, sell products or disseminate messages. Some social networks use multimedia content to promote information and create social communities. In order to increase the impact of the digital content, those images or videos are labeled with different words, denominated tags. In this paper, we propose a recommender system which analyzes multimedia content and suggests tags to maximize its influence in the social community. It implements a Case-Based Reasoning architecture (CBR), which allows to learn from previous tagged content. The system has been evaluated through cross fold validation with a training and validation sets carefully constructed and extracted from Instagram. The results demonstrate that the system can suggest good options to label our image and maximize the influence of the multimedia content.