We present an estimator based upon the combination of two powerful statistical tools that appears to be sensitive enough to detect tiny deviations from Gaussianity in CMB maps: the Minkowski Functionals, widely used to study non-Gaussian signals, and Neural Networks, designed to identify patterns in a data set. We test our estimator by analyzing simulated CMB maps contaminated with different amounts of local primordial non-Gaussianity, quantified by the dimensionless parameter f_NL. Applying it to sets of simulated maps we find >~98% of chance of positive detection, even for small intensity local non-Gaussianity like f_NL=38±18, the current limit set by the Planck satellite for large angular scales.