Content-basis image retrieval is important option to prevail within the difficulties of previous works and contains attracted an excellent concentration in past decades. The models according to graph-based ranking were mostly analysed and extensively functional in file recovery area. Within our work we concentrate on the novel in addition to efficient graph-based model for content based image retrieval, designed for out-of-sample recovery on extensive databases. We advise a scalable graph-based ranking representation referred to as effective Manifold Ranking, which address weak points of Manifold Ranking from two most significant viewpoints for example scalable graph construction in addition to effective ranking computation. We concentrate on a famous graph-based model known Manifold Ranking that is a well-known graph-based ranking representation that ranks data samples relevant to intrinsic geometrical structure uncovered with a huge data. The suggested model includes two separate stages just like an offline stage for structuring of ranking model plus an online stage for controlling of recent query. Using the suggested system, we are able to handle database by a million images and perform online retrieval inside a short instance.