Identifying organisms is a key step in accessing information related to the ecology of species. But unfortunately, this is difficult to achieve due to the level of expertise necessary to correctly identify and record living organisms. To try bridging this gap, enormous work has been done on the development of automated species identification tools such as image-based plant identification or audio recordings-based bird identification. Yet, for some groups, it is preferable to monitor the organisms at the individual level rather than at the species level. The automatizing of this problem has received much less attention than species identification. In this paper, we address the specific scenario of discovering humpack whales individuals in a large collections of pictures collected by nature observers. The process is initiated from scratch, without any knowledge on the number of individuals and without any training samples of these individuals. Thus, the problem is entirely unsupervised. To address it, we set up and experimented a scalable fine-grained matching system allowing to discover small rigid visual patterns in highly clutter background. The evaluation was conducted in blind in the context of the LifeCLEF evaluation campaign. Results show that the proposed system provides very promising results with regard to the difficulty of the task but that there is still room for improvements to reach higher recall and precision in the future.