Brain-Computer-Interfaces (BCIs) that decode aesthetic Interest could improve user experience in digital spaces by personalizing aesthetic stimuli selection without requir- ing explicit user feedback that might interrupt aesthetic experience. However, scientific understanding of aesthetic experience remains lacking, while validated BCI methods have not yet been applied to decode aesthetic Interest from EEG. We thus conducted a study in which participants gazed at visual art in a virtual museum and graded their Interest for each of them, while their EEG was being measured. Previous research suggested that brain oscillations could be informative of aesthetic preference. There- fore, we tested Filterbank Common Spatial Patterns feature extraction together with shrinkage Linear Discriminant Analysis, in a 2-class aesthetic Interest classification problem. We report promising aesthetic Interest decoding accuracies significantly and substantially above chance level.